{ "best_metric": 3.911320447921753, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/0/checkpoints/checkpoint-305280", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 305280, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.9819, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8109, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.191, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9683, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.803, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.6962, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.5926, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.52, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4384, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3919, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3319, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.2903, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2461, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2002, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1624, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1206, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.0928, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0621, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.98490857024181e-05, "loss": 5.035, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984069975490758e-05, "loss": 5.0055, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983231380739706e-05, "loss": 4.9923, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9647, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9352, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9223, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9113, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8755, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 4.8571, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.846, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8307, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8077, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 4.7903, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7884, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7724, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7664, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7516, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7332, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7271, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.6934, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7001, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6722, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6729, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6598, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6628, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6413, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6367, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.63, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6121, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.623, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5882, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5808, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5924, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5887, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.565, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5567, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5574, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5389, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5611, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5212, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5329, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5215, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5065, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5152, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.4986, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4946, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4843, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4986, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4717, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4756, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4531, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4628, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4738, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4646, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.447, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4592, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4597, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.434, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4407, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4226, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4148, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4117, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4124, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4179, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4238, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930422841748654e-05, "loss": 4.4144, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3893, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.3948, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.3976, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927070100624819e-05, "loss": 4.3892, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3798, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3773, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3723, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3802, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.9228804026303046e-05, "loss": 4.3674, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922041807879253e-05, "loss": 4.3732, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921203213128201e-05, "loss": 4.3643, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3622, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3465, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3496, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3468, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3516, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3518, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3292, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.336, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3284, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3328, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3189, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3165, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3241, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3138, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3106, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.303, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3008, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.9061134212503846e-05, "loss": 4.3136, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3015, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3016, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3044, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027606801265495e-05, "loss": 4.3093, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.2939, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2821, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.289, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2938, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985693442516624e-05, "loss": 4.2806, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2796, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.277, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2791, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2731, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2757, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2673, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2693, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2617, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2794, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2627, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2554, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2516, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.2607, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.2549, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2604, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.247, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2529, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2473, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2471, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2375, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2478, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.2354, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2258, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2472, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.2313, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2294, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2391, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2202, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.1929707527160645, "eval_runtime": 303.6122, "eval_samples_per_second": 1256.837, "eval_steps_per_second": 39.277, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.21, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2134, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.2211, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2135, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2212, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.2058, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.209, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.1986, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2129, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.1954, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.1943, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.1977, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.1939, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.1855, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.1868, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1708, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1818, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.1743, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.1688, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.1941, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1726, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1747, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.1715, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1866, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1592, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1627, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.167, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.1656, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1547, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.154, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1615, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1619, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1629, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1552, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.1487, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1564, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1319, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1513, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842404788376029e-05, "loss": 4.1307, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.1399, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1361, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1457, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.8390520472521936e-05, "loss": 4.1379, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382134525011416e-05, "loss": 4.1314, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.1365, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1282, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835699306128359e-05, "loss": 4.1406, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834860711377307e-05, "loss": 4.1134, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.1139, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833183521875203e-05, "loss": 4.131, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832346565004524e-05, "loss": 4.1334, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831507970253472e-05, "loss": 4.1175, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.83066937550242e-05, "loss": 4.1132, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829830780751368e-05, "loss": 4.121, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.1037, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828155229129637e-05, "loss": 4.1295, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273166343785856e-05, "loss": 4.1088, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264780396275336e-05, "loss": 4.1174, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256410827568545e-05, "loss": 4.1124, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248024880058025e-05, "loss": 4.0996, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239638932547505e-05, "loss": 4.1148, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231252985036985e-05, "loss": 4.1013, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222867037526465e-05, "loss": 4.0995, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.0965, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206111521309154e-05, "loss": 4.1139, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197725573798634e-05, "loss": 4.0967, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189339626288114e-05, "loss": 4.0963, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.087, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817258411007081e-05, "loss": 4.0938, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816419816256029e-05, "loss": 4.1099, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815581221504977e-05, "loss": 4.1053, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.0935, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813905669883246e-05, "loss": 4.1029, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813067075132194e-05, "loss": 4.1067, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812228480381141e-05, "loss": 4.0916, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811389885630089e-05, "loss": 4.0973, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810552928759411e-05, "loss": 4.0873, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809714334008359e-05, "loss": 4.0784, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808875739257306e-05, "loss": 4.0801, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808037144506255e-05, "loss": 4.0843, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807200187635576e-05, "loss": 4.0874, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063615928845243e-05, "loss": 4.1034, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055229981334717e-05, "loss": 4.0908, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046844033824197e-05, "loss": 4.0694, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803847446511741e-05, "loss": 4.0781, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030088517606886e-05, "loss": 4.0839, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021702570096366e-05, "loss": 4.0813, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013316622585846e-05, "loss": 4.0713, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800494705387906e-05, "loss": 4.0733, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996561106368535e-05, "loss": 4.0716, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988175158858015e-05, "loss": 4.0769, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0684, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797141964264071e-05, "loss": 4.0775, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796303369513019e-05, "loss": 4.0719, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795464774761967e-05, "loss": 4.0736, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.056, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793789223140236e-05, "loss": 4.0674, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792950628389184e-05, "loss": 4.0622, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792112033638132e-05, "loss": 4.0683, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.79127343888708e-05, "loss": 4.0675, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790436482016401e-05, "loss": 4.0582, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789597887265349e-05, "loss": 4.06, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788759292514297e-05, "loss": 4.0584, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787920697763245e-05, "loss": 4.0615, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870837408925664e-05, "loss": 4.0484, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786246784021888e-05, "loss": 4.0508, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785408189270836e-05, "loss": 4.06, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784569594519783e-05, "loss": 4.0503, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783730999768731e-05, "loss": 4.0502, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782892405017679e-05, "loss": 4.044, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782053810266627e-05, "loss": 4.0421, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781215215515575e-05, "loss": 4.0629, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780376620764523e-05, "loss": 4.045, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779539663893844e-05, "loss": 4.0533, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778701069142792e-05, "loss": 4.0513, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.77786247439174e-05, "loss": 4.0634, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777025517521062e-05, "loss": 4.0496, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.77618692277001e-05, "loss": 4.0355, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775348328018958e-05, "loss": 4.044, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774509733267906e-05, "loss": 4.0511, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773671138516854e-05, "loss": 4.036, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728341816461747e-05, "loss": 4.0403, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719955868951227e-05, "loss": 4.0369, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711569921440707e-05, "loss": 4.0474, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703183973930186e-05, "loss": 4.0344, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694798026419666e-05, "loss": 4.0439, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686412078909146e-05, "loss": 4.036, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7678026131398626e-05, "loss": 4.0382, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766965656269184e-05, "loss": 4.0298, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766127061518132e-05, "loss": 4.0513, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528846676708e-05, "loss": 4.0418, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764449872016028e-05, "loss": 4.0265, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763612915145349e-05, "loss": 4.0289, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762774320394297e-05, "loss": 4.0373, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761935725643245e-05, "loss": 4.0364, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761097130892193e-05, "loss": 4.0444, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760260174021514e-05, "loss": 4.0279, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759421579270462e-05, "loss": 4.0357, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.75858298451941e-05, "loss": 4.0293, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757744389768358e-05, "loss": 4.0357, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569074328976796e-05, "loss": 4.0265, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560688381466276e-05, "loss": 4.0314, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552302433955756e-05, "loss": 4.0237, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543916486445236e-05, "loss": 4.018, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535546917738445e-05, "loss": 4.0388, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527160970227925e-05, "loss": 4.0253, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518775022717405e-05, "loss": 4.022, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510389075206885e-05, "loss": 4.0264, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7502003127696365e-05, "loss": 4.0177, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.026247978210449, "eval_runtime": 304.5864, "eval_samples_per_second": 1252.817, "eval_steps_per_second": 39.151, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493617180185845e-05, "loss": 4.0071, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748523123267532e-05, "loss": 4.0095, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.74768452851648e-05, "loss": 4.0252, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746845933765428e-05, "loss": 4.0124, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460073390143764e-05, "loss": 4.0264, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451687442633244e-05, "loss": 4.0096, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443301495122724e-05, "loss": 4.012, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434915547612204e-05, "loss": 4.0067, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0207, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0062, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0046, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740138813637385e-05, "loss": 4.0032, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739303494647079e-05, "loss": 4.0055, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738464899896027e-05, "loss": 3.9975, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737626305144975e-05, "loss": 4.0014, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736787710393923e-05, "loss": 3.9905, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735949115642871e-05, "loss": 3.9945, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.73511052089182e-05, "loss": 3.9904, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734271926140768e-05, "loss": 3.9857, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733433331389716e-05, "loss": 4.0199, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732594736638664e-05, "loss": 3.9938, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731756141887612e-05, "loss": 3.9901, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73091754713656e-05, "loss": 3.997, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730080590265881e-05, "loss": 4.0043, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292436333952016e-05, "loss": 3.9825, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7284050386441496e-05, "loss": 3.991, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275664438930976e-05, "loss": 3.9905, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267278491420456e-05, "loss": 3.9943, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.9799, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250506596399416e-05, "loss": 3.9855, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242120648888896e-05, "loss": 3.9876, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723373470137838e-05, "loss": 3.9938, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722536513267159e-05, "loss": 3.9991, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721697918516107e-05, "loss": 3.9877, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720859323765055e-05, "loss": 3.9806, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720020729014003e-05, "loss": 3.9915, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719183772143324e-05, "loss": 3.9727, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718346815272645e-05, "loss": 3.9854, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717508220521593e-05, "loss": 3.9675, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716669625770541e-05, "loss": 3.9742, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715831031019489e-05, "loss": 3.978, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714992436268437e-05, "loss": 3.9854, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9804, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713315246766333e-05, "loss": 3.9731, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712476652015281e-05, "loss": 3.9779, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116396951446025e-05, "loss": 3.9731, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108011003935505e-05, "loss": 3.9817, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709962505642498e-05, "loss": 3.9597, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091255487718194e-05, "loss": 3.9587, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082869540207674e-05, "loss": 3.9771, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074483592697154e-05, "loss": 3.9757, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706609764518663e-05, "loss": 3.9645, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705771169767611e-05, "loss": 3.9632, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704932575016559e-05, "loss": 3.9681, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.70409561814588e-05, "loss": 3.9525, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703257023394828e-05, "loss": 3.9745, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702418428643776e-05, "loss": 3.9614, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701579833892724e-05, "loss": 3.9693, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700741239141672e-05, "loss": 3.9634, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990264439062e-05, "loss": 3.9589, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699064049639568e-05, "loss": 3.9596, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698225454888516e-05, "loss": 3.9595, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697388498017837e-05, "loss": 3.9533, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696549903266785e-05, "loss": 3.9506, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695711308515733e-05, "loss": 3.9668, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694872713764681e-05, "loss": 3.9545, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694035756894003e-05, "loss": 3.9553, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693197162142951e-05, "loss": 3.9445, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692358567391899e-05, "loss": 3.9511, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691519972640847e-05, "loss": 3.9683, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906846536505406e-05, "loss": 3.9639, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.6898460588994886e-05, "loss": 3.9555, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890074641484366e-05, "loss": 3.9634, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881688693973846e-05, "loss": 3.9675, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873302746463326e-05, "loss": 3.9498, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864916798952806e-05, "loss": 3.9577, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856547230246015e-05, "loss": 3.9514, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848161282735495e-05, "loss": 3.9438, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683977533522498e-05, "loss": 3.9509, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683138938771446e-05, "loss": 3.944, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682300344020394e-05, "loss": 3.9527, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681461749269342e-05, "loss": 3.9631, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.68062315451829e-05, "loss": 3.9597, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679786197647611e-05, "loss": 3.9321, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678947602896559e-05, "loss": 3.9492, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678109008145507e-05, "loss": 3.9501, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677270413394455e-05, "loss": 3.9493, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676433456523776e-05, "loss": 3.9429, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675594861772724e-05, "loss": 3.9371, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674756267021672e-05, "loss": 3.9463, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.67391767227062e-05, "loss": 3.9422, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730807153999415e-05, "loss": 3.9384, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722421206488895e-05, "loss": 3.949, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6714035258978375e-05, "loss": 3.9409, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705649311467855e-05, "loss": 3.9483, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697263363957335e-05, "loss": 3.9321, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688893795250544e-05, "loss": 3.9365, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680507847740024e-05, "loss": 3.9374, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6672121900229504e-05, "loss": 3.9457, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663735952718984e-05, "loss": 3.9416, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665536638401219e-05, "loss": 3.933, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664698043650167e-05, "loss": 3.9362, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663859448899115e-05, "loss": 3.9332, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663020854148063e-05, "loss": 3.9374, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662182259397011e-05, "loss": 3.9222, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661345302526333e-05, "loss": 3.9255, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660506707775281e-05, "loss": 3.9428, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659668113024229e-05, "loss": 3.9317, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658829518273176e-05, "loss": 3.9253, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657992561402498e-05, "loss": 3.9232, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657153966651446e-05, "loss": 3.9233, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656315371900393e-05, "loss": 3.9391, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655476777149341e-05, "loss": 3.9298, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654638182398289e-05, "loss": 3.9282, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6538012255276106e-05, "loss": 3.9304, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529626307765586e-05, "loss": 3.9459, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.6521240360255066e-05, "loss": 3.9325, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.6512854412744546e-05, "loss": 3.9187, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650448484403776e-05, "loss": 3.9286, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.6496098896527235e-05, "loss": 3.9302, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.6487712949016715e-05, "loss": 3.9214, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479327001506195e-05, "loss": 3.9239, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470941053995675e-05, "loss": 3.9207, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462571485288884e-05, "loss": 3.9315, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454185537778364e-05, "loss": 3.9177, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445799590267844e-05, "loss": 3.932, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437413642757324e-05, "loss": 3.9149, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429027695246804e-05, "loss": 3.9267, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642065812654002e-05, "loss": 3.9149, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.64122721790295e-05, "loss": 3.9377, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640388623151898e-05, "loss": 3.9297, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639550028400846e-05, "loss": 3.9194, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638713071530167e-05, "loss": 3.9122, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637874476779115e-05, "loss": 3.9253, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637035882028063e-05, "loss": 3.9225, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636197287277011e-05, "loss": 3.9323, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635358692525959e-05, "loss": 3.915, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.63452173565528e-05, "loss": 3.9273, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633683140904228e-05, "loss": 3.92, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632844546153176e-05, "loss": 3.9309, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320059514021244e-05, "loss": 3.9137, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311673566510724e-05, "loss": 3.9227, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303303997803934e-05, "loss": 3.9161, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.6294918050293413e-05, "loss": 3.9093, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286532102782893e-05, "loss": 3.9275, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278146155272373e-05, "loss": 3.9229, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626976020776185e-05, "loss": 3.91, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626137426025133e-05, "loss": 3.9211, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625298831274081e-05, "loss": 3.9112, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.953259229660034, "eval_runtime": 312.5733, "eval_samples_per_second": 1220.805, "eval_steps_per_second": 38.151, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624461874403402e-05, "loss": 3.9069, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.62362327965235e-05, "loss": 3.9035, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622784684901298e-05, "loss": 3.9145, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621946090150246e-05, "loss": 3.9111, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621109133279568e-05, "loss": 3.9243, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620270538528516e-05, "loss": 3.9013, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619431943777464e-05, "loss": 3.9091, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618593349026412e-05, "loss": 3.9022, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617754754275359e-05, "loss": 3.921, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616916159524307e-05, "loss": 3.9018, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616079202653629e-05, "loss": 3.8978, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615240607902577e-05, "loss": 3.9052, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144036510318976e-05, "loss": 3.901, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135650562808456e-05, "loss": 3.8982, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127264615297936e-05, "loss": 3.8991, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118878667787416e-05, "loss": 3.8923, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110492720276896e-05, "loss": 3.8901, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102106772766376e-05, "loss": 3.8921, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093720825255856e-05, "loss": 3.8879, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085334877745336e-05, "loss": 3.919, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6076965309038545e-05, "loss": 3.8928, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.6068579361528025e-05, "loss": 3.8933, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6060193414017505e-05, "loss": 3.8986, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051807466506985e-05, "loss": 3.9037, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043437897800194e-05, "loss": 3.8894, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035051950289674e-05, "loss": 3.8957, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026666002779154e-05, "loss": 3.8906, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018280055268634e-05, "loss": 3.8953, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600991048656185e-05, "loss": 3.885, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600152453905133e-05, "loss": 3.8884, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599313859154081e-05, "loss": 3.8939, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598475264403029e-05, "loss": 3.8965, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597636669651977e-05, "loss": 3.9021, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596799712781298e-05, "loss": 3.8945, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595961118030246e-05, "loss": 3.8846, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595122523279194e-05, "loss": 3.8946, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594283928528142e-05, "loss": 3.8812, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593446971657463e-05, "loss": 3.8886, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592608376906411e-05, "loss": 3.8744, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591769782155359e-05, "loss": 3.8805, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590931187404307e-05, "loss": 3.8808, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590094230533628e-05, "loss": 3.8946, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589255635782576e-05, "loss": 3.8889, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588417041031524e-05, "loss": 3.8808, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587578446280472e-05, "loss": 3.8842, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.58673985152942e-05, "loss": 3.8822, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585902894658741e-05, "loss": 3.8892, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585064299907689e-05, "loss": 3.8715, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584225705156637e-05, "loss": 3.8672, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583387110405585e-05, "loss": 3.8874, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582550153534906e-05, "loss": 3.8856, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581711558783854e-05, "loss": 3.8694, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580872964032802e-05, "loss": 3.8769, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580034369281751e-05, "loss": 3.8801, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579197412411072e-05, "loss": 3.8646, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.57835881766002e-05, "loss": 3.8824, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577520222908968e-05, "loss": 3.87, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576681628157916e-05, "loss": 3.8845, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758446712872366e-05, "loss": 3.8699, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5750060765361846e-05, "loss": 3.879, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741674817851326e-05, "loss": 3.8674, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733288870340806e-05, "loss": 3.8727, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724902922830286e-05, "loss": 3.8613, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716516975319765e-05, "loss": 3.8649, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708147406612975e-05, "loss": 3.8832, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569976145910246e-05, "loss": 3.8643, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569137551159194e-05, "loss": 3.8701, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568298956408142e-05, "loss": 3.8572, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567461999537463e-05, "loss": 3.8676, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566623404786411e-05, "loss": 3.8817, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565784810035359e-05, "loss": 3.8769, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564946215284307e-05, "loss": 3.8738, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564109258413628e-05, "loss": 3.8793, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563270663662576e-05, "loss": 3.8779, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562432068911524e-05, "loss": 3.8676, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561593474160472e-05, "loss": 3.8702, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560756517289793e-05, "loss": 3.8705, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599179225387415e-05, "loss": 3.862, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590793277876895e-05, "loss": 3.8631, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.5582407330366375e-05, "loss": 3.8619, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.5574037761659584e-05, "loss": 3.867, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.5565651814149064e-05, "loss": 3.8786, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.5557265866638544e-05, "loss": 3.8748, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.5548879919128024e-05, "loss": 3.8482, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.55404939716175e-05, "loss": 3.8694, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553212440291071e-05, "loss": 3.8662, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552373845540019e-05, "loss": 3.8653, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.5515352507889666e-05, "loss": 3.8609, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550696656037915e-05, "loss": 3.8521, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549859699167237e-05, "loss": 3.8665, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549021104416185e-05, "loss": 3.8597, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548182509665132e-05, "loss": 3.8594, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.54734391491408e-05, "loss": 3.8659, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546506958043402e-05, "loss": 3.8612, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.54566836329235e-05, "loss": 3.8701, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544829768541297e-05, "loss": 3.8539, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543991173790245e-05, "loss": 3.8529, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431542169195667e-05, "loss": 3.8558, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542315622168514e-05, "loss": 3.8692, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541477027417462e-05, "loss": 3.8589, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406384326664106e-05, "loss": 3.8536, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.5397998379153586e-05, "loss": 3.8529, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.5389628810446796e-05, "loss": 3.8564, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.5381242862936275e-05, "loss": 3.8647, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.5372856915425755e-05, "loss": 3.8479, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364470967915235e-05, "loss": 3.8461, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5356101399208444e-05, "loss": 3.8624, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347715451697924e-05, "loss": 3.8514, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339329504187404e-05, "loss": 3.8475, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330943556676884e-05, "loss": 3.8429, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322573987970093e-05, "loss": 3.8481, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314188040459573e-05, "loss": 3.8629, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530580209294906e-05, "loss": 3.8462, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529741614543854e-05, "loss": 3.851, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528904657673175e-05, "loss": 3.8565, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528066062922123e-05, "loss": 3.8667, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527227468171071e-05, "loss": 3.8612, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526388873420019e-05, "loss": 3.841, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.52555191654934e-05, "loss": 3.853, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.524713321798288e-05, "loss": 3.8499, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.523874727047236e-05, "loss": 3.8482, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.523037770176557e-05, "loss": 3.8496, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.522199175425505e-05, "loss": 3.8417, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.521360580674453e-05, "loss": 3.8555, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520521985923401e-05, "loss": 3.844, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.5196833911723494e-05, "loss": 3.8532, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.5188447964212974e-05, "loss": 3.8427, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.5180062016702454e-05, "loss": 3.8509, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.5171676069191934e-05, "loss": 3.8389, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516330650048514e-05, "loss": 3.8669, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515492055297462e-05, "loss": 3.8475, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.51465346054641e-05, "loss": 3.8495, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513814865795358e-05, "loss": 3.8381, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512977908924679e-05, "loss": 3.8544, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512139314173627e-05, "loss": 3.8478, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511300719422575e-05, "loss": 3.855, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510462124671523e-05, "loss": 3.8435, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509625167800845e-05, "loss": 3.8521, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.508786573049793e-05, "loss": 3.8471, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.507947978298741e-05, "loss": 3.8602, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507109383547689e-05, "loss": 3.8374, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062724266770096e-05, "loss": 3.8512, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054338319259576e-05, "loss": 3.8433, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045952371749056e-05, "loss": 3.8406, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037566424238536e-05, "loss": 3.8502, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5029180476728016e-05, "loss": 3.8499, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020810908021225e-05, "loss": 3.8395, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012424960510705e-05, "loss": 3.8435, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.5004039013000185e-05, "loss": 3.8429, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.911320447921753, "eval_runtime": 357.6326, "eval_samples_per_second": 1066.992, "eval_steps_per_second": 33.344, "step": 305280 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.10997743962923e+17, "trial_name": null, "trial_params": null }